{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PS34RS6EAWSHIPBCHJIK7BUDAL","short_pith_number":"pith:PS34RS6E","canonical_record":{"source":{"id":"2302.00894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T06:01:50Z","cross_cats_sorted":[],"title_canon_sha256":"5ffca64797530b1a7f3861dc802c63a4bee1f3ad0e2c05393c39d378bb052c41","abstract_canon_sha256":"ee49331c7bf64a585fbbf552726dbd7c6a50dcb6c6d938b41a12c04e55cbf37b"},"schema_version":"1.0"},"canonical_sha256":"7cb7c8cbc405a4743c223a50af868302f0c1e14bcd0f3d89c034f6b91411ad83","source":{"kind":"arxiv","id":"2302.00894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00894","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00894v1","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00894","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"PS34RS6EAWSH","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"PS34RS6EAWSHIPBC","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"PS34RS6E","created_at":"2026-07-05T05:38:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PS34RS6EAWSHIPBCHJIK7BUDAL","target":"record","payload":{"canonical_record":{"source":{"id":"2302.00894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T06:01:50Z","cross_cats_sorted":[],"title_canon_sha256":"5ffca64797530b1a7f3861dc802c63a4bee1f3ad0e2c05393c39d378bb052c41","abstract_canon_sha256":"ee49331c7bf64a585fbbf552726dbd7c6a50dcb6c6d938b41a12c04e55cbf37b"},"schema_version":"1.0"},"canonical_sha256":"7cb7c8cbc405a4743c223a50af868302f0c1e14bcd0f3d89c034f6b91411ad83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:13.803000Z","signature_b64":"T0Uc4b4rGFlnscENlij3MWb5A3sq31beDEYqaq19Q+1PnF/i2y8jHoGyCXvXhr/eNOAuQVRGQpASzw7W0jKdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cb7c8cbc405a4743c223a50af868302f0c1e14bcd0f3d89c034f6b91411ad83","last_reissued_at":"2026-07-05T05:38:13.802529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:13.802529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.00894","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OclW6Bwm5++OOuU1IZyciuibF8Yf4BgCR8A6Z4cO+3gfHYslVV7gt+zUwASjO0I6FUn41bXaa2xgHxRPQpCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:12:20.751522Z"},"content_sha256":"73bf022c5a7e42ab2271ce7ad732621b03cf9ace03f660a7fa2b8fc761767dfb","schema_version":"1.0","event_id":"sha256:73bf022c5a7e42ab2271ce7ad732621b03cf9ace03f660a7fa2b8fc761767dfb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PS34RS6EAWSHIPBCHJIK7BUDAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to choose \"Good\" Samples for Text Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nankai Lin, Shengyi Jiang, Xiaotian Lin, Yingwen Fu, Ziyu Yang","submitted_at":"2023-02-02T06:01:50Z","abstract_excerpt":"Deep learning-based text classification models need abundant labeled data to obtain competitive performance. Unfortunately, annotating large-size corpus is time-consuming and laborious. To tackle this, multiple researches try to use data augmentation to expand the corpus size. However, data augmentation may potentially produce some noisy augmented samples. There are currently no works exploring sample selection for augmented samples in nature language processing field. In this paper, we propose a novel self-training selection framework with two selectors to select the high-quality samples from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00894","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.00894/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgT4A7Iz8K6wII7fZ9KJayZNSQDsgyf9u/wsW3W6oXXAWw6/iAY4VmR7ikcRfy/YxsZuAOmzt51ahGb/SFIgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:12:20.751888Z"},"content_sha256":"abb7689f0843003b7ddfafa94d73de6d901094026a94112f1460b71eaa9b8cbe","schema_version":"1.0","event_id":"sha256:abb7689f0843003b7ddfafa94d73de6d901094026a94112f1460b71eaa9b8cbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PS34RS6EAWSHIPBCHJIK7BUDAL/bundle.json","state_url":"https://pith.science/pith/PS34RS6EAWSHIPBCHJIK7BUDAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PS34RS6EAWSHIPBCHJIK7BUDAL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T03:12:20Z","links":{"resolver":"https://pith.science/pith/PS34RS6EAWSHIPBCHJIK7BUDAL","bundle":"https://pith.science/pith/PS34RS6EAWSHIPBCHJIK7BUDAL/bundle.json","state":"https://pith.science/pith/PS34RS6EAWSHIPBCHJIK7BUDAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PS34RS6EAWSHIPBCHJIK7BUDAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PS34RS6EAWSHIPBCHJIK7BUDAL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee49331c7bf64a585fbbf552726dbd7c6a50dcb6c6d938b41a12c04e55cbf37b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T06:01:50Z","title_canon_sha256":"5ffca64797530b1a7f3861dc802c63a4bee1f3ad0e2c05393c39d378bb052c41"},"schema_version":"1.0","source":{"id":"2302.00894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00894","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00894v1","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00894","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"PS34RS6EAWSH","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"PS34RS6EAWSHIPBC","created_at":"2026-07-05T05:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"PS34RS6E","created_at":"2026-07-05T05:38:13Z"}],"graph_snapshots":[{"event_id":"sha256:abb7689f0843003b7ddfafa94d73de6d901094026a94112f1460b71eaa9b8cbe","target":"graph","created_at":"2026-07-05T05:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.00894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning-based text classification models need abundant labeled data to obtain competitive performance. Unfortunately, annotating large-size corpus is time-consuming and laborious. To tackle this, multiple researches try to use data augmentation to expand the corpus size. However, data augmentation may potentially produce some noisy augmented samples. There are currently no works exploring sample selection for augmented samples in nature language processing field. In this paper, we propose a novel self-training selection framework with two selectors to select the high-quality samples from","authors_text":"Nankai Lin, Shengyi Jiang, Xiaotian Lin, Yingwen Fu, Ziyu Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T06:01:50Z","title":"How to choose \"Good\" Samples for Text Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00894","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:73bf022c5a7e42ab2271ce7ad732621b03cf9ace03f660a7fa2b8fc761767dfb","target":"record","created_at":"2026-07-05T05:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee49331c7bf64a585fbbf552726dbd7c6a50dcb6c6d938b41a12c04e55cbf37b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-02T06:01:50Z","title_canon_sha256":"5ffca64797530b1a7f3861dc802c63a4bee1f3ad0e2c05393c39d378bb052c41"},"schema_version":"1.0","source":{"id":"2302.00894","kind":"arxiv","version":1}},"canonical_sha256":"7cb7c8cbc405a4743c223a50af868302f0c1e14bcd0f3d89c034f6b91411ad83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cb7c8cbc405a4743c223a50af868302f0c1e14bcd0f3d89c034f6b91411ad83","first_computed_at":"2026-07-05T05:38:13.802529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:13.802529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T0Uc4b4rGFlnscENlij3MWb5A3sq31beDEYqaq19Q+1PnF/i2y8jHoGyCXvXhr/eNOAuQVRGQpASzw7W0jKdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:13.803000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.00894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73bf022c5a7e42ab2271ce7ad732621b03cf9ace03f660a7fa2b8fc761767dfb","sha256:abb7689f0843003b7ddfafa94d73de6d901094026a94112f1460b71eaa9b8cbe"],"state_sha256":"dbe4e4ceba46e09b6899ca56bddab903c7a809009e8761678e2675b2dea0936c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z56ZUdGZQjLeIi0cu7JTsz6wbyCarRXejXW+B2QMrJsdt4HoOI4SFEIxlaHIY8UJLkAB5dmbmaCYV+o0C65kDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:12:20.755482Z","bundle_sha256":"ba813d7c785cc73a48b0d88fc321bbf60c356318109913cdc2c454421a117999"}}